Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 228 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0750. Min Range: -13.0750
Max Act: 13.0750. Min Act: -0.1700
Data Index: 1857147 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0750. Min Range: -13.0750
Max Act: 13.0125. Min Act: -0.1700
Data Index: 1361173 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.9500. Min Act: -0.1700
Data Index: 3769936 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.8875. Min Act: -0.1700
Data Index: 1170917 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.8250. Min Act: -0.1700
Data Index: 3453444 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.7625. Min Act: -0.1700
Data Index: 1202236 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.7625. Min Act: -0.1700
Data Index: 2783117 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.7625. Min Act: -0.1700
Data Index: 6109484 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.7625. Min Act: -0.1700
Data Index: 3213286 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.7000. Min Act: -0.1700
Data Index: 7598143 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.7000. Min Act: -0.1700
Data Index: 2357778 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.7000. Min Act: -0.1700
Data Index: 7120691 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.6375. Min Act: -0.1700
Data Index: 4607096 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.6375. Min Act: -0.1700
Data Index: 5063260 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.6375. Min Act: -0.1700
Data Index: 7541927 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.5750. Min Act: -0.1700
Data Index: 1443664 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.5750. Min Act: -0.1700
Data Index: 1673234 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.5750. Min Act: -0.1700
Data Index: 6517271 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.6375. Min Act: -0.1700
Data Index: 3585904 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0750. Min Range: -13.0750
Max Act: 12.5750. Min Act: -0.1700
Data Index: 4731826 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19